---
title: "Quipu: A Governed Bitemporal Knowledge Graph Store That Turns Audits Into Queries"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.16813v1"
permalink: "https://feed.astralor.com/items/itm_01f0e8bef73bc4e97e901f32"
published: "2026-08-17T17:04:29.000Z"
score: 77
channel: "ai"
tags: ["Agent Governance","arXiv","Quipu","Bitemporal","Knowledge Graph"]
---

# Quipu: A Governed Bitemporal Knowledge Graph Store That Turns Audits Into Queries

## AI commentary

> Quipu's value is not another graph store; it moves governance from dashboards and middleware into the store kernel, turning audits into queries. It matters for agent-infrastructure, knowledge-graph, and compliance engineers; if you want trustworthiness and accountability for multi-agent facts, its lattice and signed-verdict design are directly worth borrowing.

## At a glance

The paper presents Quipu, an embeddable knowledge-graph store designed for agent-driven writes. It inverts four defaults of human-curated stores: no fact enters without passing a gate that evaluates the pending post-state; data, trust labels, verdicts, and rules are all bitemporal; named graphs become the unit of authority and trust, composed under a lattice whose invariant is that composition never widens; and the governance specification, trace, and signed verdicts are themselves facts in the store, making audit T ⊨ Σ a query. Evaluated on Census and DEMM-Bench, Quipu eliminates planted defects, re-derives all satisfied verdicts faithfully as of their instant, and surfaces a live enforcement gap that the audit names with its remediation.

## Key points

- Quipu combines write gates, a bitemporal data model, a named-graph trust lattice, and governance-as-in-store-queries, making audit T ⊨ Σ a query.
- In the Census multi-writer lifecycle, the gated store ends with 0 of 6 planted defects versus 6 of 6 ungated; all 7 composition probes uphold the lattice contract.
- 50 of 50 satisfied verdicts re-derive faithfully as of their instant, while all 50 would be misreported under a latest-only rule set; the SARC reference checker agrees verdict-for-verdict.
- On DEMM-Bench, content-only reading answers all 512 property-level questions with zero overclaim under all eight degradation conditions, and surfaced a gap in what a denial's verdict attests.

## Full text

Agents now write knowledge graphs, but knowledge-graph stores still carry defaults set when humans curated them: accept writes now and clean later, keep one time axis or none, treat every writer's facts as equally trustworthy, and leave governance to dashboards and middleware. These four defaults are individually convenient and jointly untenable under agent workloads. We present Quipu, an embeddable store that inverts all four: no fact enters except through a gate whose predicates evaluate the pending post-state; data, trust labels, verdicts, and the rules themselves are bitemporal; named graphs are the unit of authority and trust, composed under a lattice whose one invariant is that composition never widens; and the governance specification $Σ$, the trace, and signed verdicts are facts in the store they govern, making the audit $T \models Σ$ a query. We evaluate with Census, a deterministic multi-writer lifecycle whose single seeded run scores every research question against planted ground truth: the gated store ends with 0 of 6 planted defects versus 6 of 6 ungated; all 7 composition probes uphold the lattice contract; 50 of 50 satisfied verdicts re-derive faithfully as of their instant while all 50 would be misreported under a latest-only rule set; and the SARC reference checker agrees with the in-store audit verdict-for-verdict, differing only on coverage semantics. A recorded trace from a governed writer surfaces a live enforcement gap the audit names with its remediation. On DEMM-Bench, an external decision-evidence sufficiency benchmark, a content-only reading of the exported records answers all 512 property-level governance questions correctly with zero overclaim under all eight degradation conditions, while container-presence baselines overclaim on up to 87.5% of them -- and the run surfaced, and led us to close, a gap in what a denial's verdict attests.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_01f0e8bef73bc4e97e901f32